Do Emotional Cues Influence the Performance of Domestic Dogs in an Observational Learning Task?

Abstract

Using social information is not indiscriminate and being able to choose what to copy and from whom to copy is critical. Dogs are able to learn socially, to recognize, and respond to dog as well as human emotional expressions, and to make reputation-like inferences based on how people behave towards their owner. Yet, the mechanisms dogs use for obtaining and utilizing social information are still to be fully understood, especially concerning whether emotional cues influence dogs' social learning. Therefore, our main aim was to test the hypothesis that an emotionally charged (negative, positive, or neutral) interaction with the demonstrator of a "V" detour task prior to testing would affect subjects' performance, by: (i) changing the value of the information provided by the demonstrator or (ii) changing the valence of the learning environment. Our experimental design consisted of three phases: pre-test (subjects were allowed to solve the task alone); emotional display (dogs watched the unfamiliar human behaving in either a positive, negative or neutral way towards their owner); test (demonstrator showed the task and subjects were allowed to move freely). Only dogs that failed in pre-test were considered for analysis (n = 46). We analyzed four dependent variables: success, time to solve the task, latency to reach the fence and matching the side of demonstration. For each, we used four models (GEEs and GLMMs) to investigate the effect of (1) demographic factors; (2) experimental design factors (including emotional group); (3) behavior of the dog; and (4) side chosen and matching. All models took into account all trials (random effect included) and the first trials only. Our findings corroborate previous studies of social learning, but present no evidence to sustain our hypothesis. We discuss the possibility of our stimuli not being salient enough in a task that involves highly motivating food and relies on long and highly distracting interval between phases. Nevertheless, these results represent an important contribution to the study of dog behavior and social cognition and pave the way for further investigations.

Keywords: Canis familiaris; emotion; social cognition; social information; socially biased learning.

FIGURE 1

Schematic representation of the experimental area. The emotional display phase happened in Space A, whereas pre-test and test occurred in Space B. Dashed arrows represent the trajectory taken by the owner and dog during pre-test (with the aim of showing the dog the baited bowl placed in the inner vertex of the fence).

FIGURE 2

Graphic representation of the moment when the subject was about to be released and start the test. E1 (demonstrator) had already baited the bowl and was distant from the fence, facing the opposite side). The difference between pre-test and test is the presence of the demonstrator. Measurements shown are those from the real experiment.

FIGURE 3

Example of the emotional display phase. (A) Shows where the owner was positioned, (B) depicts a positive emotional display, and (C) depicts a negative emotional display.

FIGURE 4

Descriptives of the four dependent variables accounting the first trials, within each emotional group (negative, neutral, and positive). Shown as the proportion of success, the proportion of matching the side of demonstration and the box and whisker plot of time to solve the task and latency to reach the fence.